2023 Fiscal Year Final Research Report
Development of artificial intelligence to generate denture design
Project/Area Number |
21K10016
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 57050:Prosthodontics-related
|
Research Institution | Tokyo Medical and Dental University |
Principal Investigator |
Fueki Kenji 東京医科歯科大学, 大学院医歯学総合研究科, 教授 (30334436)
|
Co-Investigator(Kenkyū-buntansha) |
若林 則幸 東京医科歯科大学, 大学院医歯学総合研究科, 教授 (00270918)
高橋 邦彦 東京医科歯科大学, M&Dデータ科学センター, 教授 (50323259)
稲用 友佳 東京医科歯科大学, 大学院医歯学総合研究科, 助教 (50802302)
|
Project Period (FY) |
2021-04-01 – 2024-03-31
|
Keywords | 部分床義歯 / 義歯設計 / 人工知能 / 説明可能AI / 深層学習 |
Outline of Final Research Achievements |
With the aim of developing artificial intelligence to automate the design of partial dentures, we collected case information on 1,000 cases of denture design and built a database of them. Using this as training data, we attempted to construct an artificial intelligence model to predict the large coupler of dentures. Using the types of large couplers of the upper and lower jaws as outcomes, we prototyped a prediction model by deep learning using multivariate parameters such as defective sites, number of missing teeth, periodontal tissue parameters, and the shape of the missing jaw ridge as predictors, and improved it to a clinically practical level. By visualizing the contribution of the AI model to the outcome of clinical parameters, we clarified the clinical basis for predicting outcomes.
|
Free Research Field |
歯科補綴学
|
Academic Significance and Societal Importance of the Research Achievements |
部分床義歯の設計には歯列欠損の状態,残存歯と顎粘膜の3次元形態,支台歯の動揺度などの様々な臨床情報に基づき判断を要する重要なステップであり,歯科医師の経験と技量が義歯の質に大きく影響する.本研究では,義歯の設計プロセスに人工知能を導入することで,歯科医師の経験と技量に依存せず適切な設計が自動的にできるシステムを開発することを見据えて構想しており,人工知能が社会実装されれば社会的な意義は大きい.また,歯科補綴学領域への人工知能の導入は比較的遅れており,本研究の成果は歯科補綴学における先駆的な例となり学術的意義も大きい.
|